search

tobegit3hub / simple_tensorflow_serving

Generic and easy-to-use serving service for machine learning models
https://stfs.readthedocs.io
Apache License 2.0
757 stars 193 forks source link

how to delpoy a model in hdfs #49

Open Lihengwannafly opened 5 years ago

tobegit3hub commented 5 years ago

Thanks for reporting. You can pass the model path as the specified HDFS path.

We may add more detailed document about this soon.

Lihengwannafly commented 5 years ago

Thanks for reporting. You can pass the model path as the specified HDFS path.

We may add more detailed document about this soon.

simple_tensorflow_serving --model_base_path="hdfs://GZGD/171587/1/model/NeuralCF/base-model-output" --model_platform="tensorflow" I deploy the above command, but this error occurs: tensorflow.python.framework.errors_impl.NotFoundError: Could not find directory.

tobegit3hub commented 5 years ago

Could you please post the files in this HDFS directory? Try with hadoop dfs -ls hdfs://GZGD/171587/1/model/NeuralCF/base-model-output.

We have to make sure that the output path is the SavedModel files with the model version.

Lihengwannafly commented 5 years ago

Could you please post the files in this HDFS directory? Try with hadoop dfs -ls hdfs://GZGD/171587/1/model/NeuralCF/base-model-output.

We have to make sure that the output path is the SavedModel files with the model version.

image the image is the screenshots of the hdfs path

tobegit3hub commented 5 years ago

So the 1551684206 is the model version, right? And are there saved_model.pb and variables in these directories of the versions?

Lihengwannafly commented 5 years ago

So the 1551684206 is the model version, right? And are there saved_model.pb and variables in these directories of the versions?

yes, of course. By the way, I used pip to install the tool, should I switch to use docker to install latest-hdfs. image